{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L2XCQWDBHHYFNNIVC6NSFEXTEJ","short_pith_number":"pith:L2XCQWDB","schema_version":"1.0","canonical_sha256":"5eae28586139f056b515179b2292f3227fedd5d0be4b8df17c5994d121442e01","source":{"kind":"arxiv","id":"2412.03966","version":2},"attestation_state":"computed","paper":{"title":"Demonstration Selection for In-Context Learning via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Deyu Cai, Jianfei Wu, Mingzhe Li, Weijia Jia, Xubin Wang, Yichen Yuan","submitted_at":"2024-12-05T08:33:52Z","abstract_excerpt":"Diversity in demonstration selection is critical for enhancing model generalization by enabling broader coverage of structures and concepts. Constructing appropriate demonstration sets remains a key research challenge. This paper introduces the Relevance-Diversity Enhanced Selection (RDES), an innovative approach that leverages reinforcement learning (RL) frameworks to optimize the selection of diverse reference demonstrations for tasks amenable to in-context learning (ICL), particularly text classification and reasoning, in few-shot prompting scenarios. RDES employs frameworks like Q-learning"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.03966","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-05T08:33:52Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c94d77aeea70186b1edc9ce0555e72f8cd60e1a3e7c10c1389a4e0eff9006d14","abstract_canon_sha256":"887f0fc7e509d0be209e98a989a6d0cbf2cc6a767585413075fef32de0eaae30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:04.899001Z","signature_b64":"taVYOlcEFlcdxrUDd5IngChci+cd0c9pmN3l86hFFmNtRICNgYL1MHoj4I2MlbeoieEp1VMnhlJF8Rn7qlSoBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5eae28586139f056b515179b2292f3227fedd5d0be4b8df17c5994d121442e01","last_reissued_at":"2026-07-05T11:09:04.898579Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:04.898579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Demonstration Selection for In-Context Learning via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Deyu Cai, Jianfei Wu, Mingzhe Li, Weijia Jia, Xubin Wang, Yichen Yuan","submitted_at":"2024-12-05T08:33:52Z","abstract_excerpt":"Diversity in demonstration selection is critical for enhancing model generalization by enabling broader coverage of structures and concepts. Constructing appropriate demonstration sets remains a key research challenge. This paper introduces the Relevance-Diversity Enhanced Selection (RDES), an innovative approach that leverages reinforcement learning (RL) frameworks to optimize the selection of diverse reference demonstrations for tasks amenable to in-context learning (ICL), particularly text classification and reasoning, in few-shot prompting scenarios. RDES employs frameworks like Q-learning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03966","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.03966/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.03966","created_at":"2026-07-05T11:09:04.898635+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.03966v2","created_at":"2026-07-05T11:09:04.898635+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03966","created_at":"2026-07-05T11:09:04.898635+00:00"},{"alias_kind":"pith_short_12","alias_value":"L2XCQWDBHHYF","created_at":"2026-07-05T11:09:04.898635+00:00"},{"alias_kind":"pith_short_16","alias_value":"L2XCQWDBHHYFNNIV","created_at":"2026-07-05T11:09:04.898635+00:00"},{"alias_kind":"pith_short_8","alias_value":"L2XCQWDB","created_at":"2026-07-05T11:09:04.898635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12744","citing_title":"GRIP: Feedback-Guided Prompt Retrieval for Large Multimodal Models","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L2XCQWDBHHYFNNIVC6NSFEXTEJ","json":"https://pith.science/pith/L2XCQWDBHHYFNNIVC6NSFEXTEJ.json","graph_json":"https://pith.science/api/pith-number/L2XCQWDBHHYFNNIVC6NSFEXTEJ/graph.json","events_json":"https://pith.science/api/pith-number/L2XCQWDBHHYFNNIVC6NSFEXTEJ/events.json","paper":"https://pith.science/paper/L2XCQWDB"},"agent_actions":{"view_html":"https://pith.science/pith/L2XCQWDBHHYFNNIVC6NSFEXTEJ","download_json":"https://pith.science/pith/L2XCQWDBHHYFNNIVC6NSFEXTEJ.json","view_paper":"https://pith.science/paper/L2XCQWDB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.03966&json=true","fetch_graph":"https://pith.science/api/pith-number/L2XCQWDBHHYFNNIVC6NSFEXTEJ/graph.json","fetch_events":"https://pith.science/api/pith-number/L2XCQWDBHHYFNNIVC6NSFEXTEJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L2XCQWDBHHYFNNIVC6NSFEXTEJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L2XCQWDBHHYFNNIVC6NSFEXTEJ/action/storage_attestation","attest_author":"https://pith.science/pith/L2XCQWDBHHYFNNIVC6NSFEXTEJ/action/author_attestation","sign_citation":"https://pith.science/pith/L2XCQWDBHHYFNNIVC6NSFEXTEJ/action/citation_signature","submit_replication":"https://pith.science/pith/L2XCQWDBHHYFNNIVC6NSFEXTEJ/action/replication_record"}},"created_at":"2026-07-05T11:09:04.898635+00:00","updated_at":"2026-07-05T11:09:04.898635+00:00"}